WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.3.0, a vulnerability involving tool name collision and indirect prompt injection allows a malicious remote MCP server to hijack tool execution. By exploiting an ambiguous naming convention in the MCP client (mcp_{service}_{tool}), an attacker can register a malicious tool that overwrites a legitimate one (e.g., tavily_extract). This enables the attacker to redirect LLM execution flow, exfiltrate system prompts, context, and potentially execute other tools with the users privileges. This issue has been patched in version 0.3.0.
Weakness
The product uses a name or reference to access a resource, but the name/reference resolves to a resource that is outside of the intended control sphere.
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/159.html
- https://cwe.mitre.org/data/definitions/177.html
- https://cwe.mitre.org/data/definitions/48.html
- https://cwe.mitre.org/data/definitions/641.html